© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70866
    Prev
    Next
    INDEX
    Explanations

    if, equations, variables

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags numeric literals (digits and decimal numbers) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    and
    -2.27
     !!!!
    -2.06
    <em>
    -1.99
    a
    -1.99
     ™
    -1.98
                    
    -1.98
    where
    -1.98
    o
    -1.97
                
    -1.97
    
    -1.92
    POSITIVE LOGITS
     when
    2.97
     if
    2.45
     for
    2.41
     with
    2.41
     after
    2.38
     without
    2.36
     in
    2.31
     during
    2.28
     at
    2.27
     as
    2.25
    Activations Density 0.009%

    No Known Activations